Systems and methods to process electronic images to produce a tissue map visualization
Systems and methods are disclosed for analyzing an image of a slide corresponding to a specimen, the method including receiving at least one digitized image of a pathology specimen; determining, using the digitized image at an artificial intelligence (AI) system, at least one salient feature, the at least one salient comprising a biomarker, cancer, cancer grade, parasite, toxicity, inflammation, and/or cancer sub-type; determining, at the AI system, a salient region overlay for the digitized image, wherein the AI system indicates a value for each pixel; and suppressing, based on the value for each pixel, one or more non-salient regions of the digitized image.
1. A computer-implemented method for analyzing an image of a slide corresponding to a pathology specimen, the method comprising:
determining, using an artificial intelligence (AI) system, a salient region overlay for at least one digitized image of the pathology specimen;
representing the salient region overlay by a set of super-pixels associated with a score;
suppressing, based on a diagnostic value for each pixel, one or more non-salient regions of the at least one digitized image; and
normalizing the salient region overlay to obtain a variable, the salient region overlay represented by a binary segmentation of the at least one digitized image indicating if each pixel has a salient feature present.
2. The computer-implemented method of claim 1 , further comprising converting the salient region overlay into a tissue map.
3. The computer-implemented method of claim 1 , further comprising:
detecting the salient feature using the Al system on the at least one digitized image to produce a tissue visualization.
4. The computer-implemented method of claim 1 , wherein the at least one digitized image comprises related case information, patient information and information from a clinical system.
5. The computer-implemented method of claim 1 , further comprising alerting a user when the salient region overlay is available.
6. The computer-implemented method of claim 1 , further comprising resizing the salient region overlay to a same size as the at least one digitized image.
7. The computer-implemented method of claim 1 , further comprising:
indicating, by the Al system, a diagnostic value for each pixel.
8. The computer-implemented method of claim 1 , further comprising representing the salient region overlay by a semantic segmentation of the at least one digitized image indicating a score or probability for each pixel.
9. A system for analyzing an image of a slide corresponding to a pathology specimen, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
determining, using an artificial intelligence (AI) system, a salient region overlay for at least one digitized image of the pathology specimen;
representing the salient region overlay by a set of super-pixels associated with a score;
suppressing, based on a diagnostic value for each pixel, one or more non-salient regions of the at least one digitized image; and
normalizing the salient region overlay to obtain a variable, the salient region overlay represented by a binary segmentation of the at least one digitized image indicating if each pixel has a salient feature present.
10. The system of claim 9 , the operations further comprising:
converting the salient region overlay into a tissue map.
11. The system of claim 9 , the operations further comprising:
detecting the salient feature using machine learning on the at least one digitized image to produce a tissue visualization.
12. The system of claim 9 , the operations further comprising developing a pipeline to archive prospective patient data.
13. The system of claim 9 , the operations further comprising representing the salient region overlay by a semantic segmentation of the at least one digitized image indicating a score or probability for each pixel.
14. A computer-implemented method for analyzing an image of a slide corresponding to a pathology specimen, the method comprising:
determining, using an artificial intelligence (AI) system, a salient region overlay for at least one digitized image of the pathology specimen;
suppressing, based on a diagnostic value for each pixel, one or more non-salient regions of the at least one digitized image;
normalizing the salient region overlay to obtain a variable, the salient region overlay represented by a binary segmentation of the at least one digitized image indicating if each pixel has a salient feature present; and
representing the salient region overlay by a semantic segmentation of the at least one digitized image indicating a score or probability for each pixel.
15. The computer-implemented method of of claim 14 , further comprising converting the salient region overlay into a tissue map.
16. The computer-implemented method of of claim 14 , further comprising: detecting the salient feature using the AI system on the at least one digitized image to produce a tissue visualization.
17. The computer-implemented method of of claim 14 , further comprising: resizing the salient region overlay to a same size as the at least one digitized image.
18. The computer-implemented method of of claim 14 , further comprising: indicating, by the AI system, a diagnostic value for each pixel.
19. A system for analyzing an image of a slide corresponding to a pathology specimen, the system comprising:
at least one memory storing instructions; and
at least one processor configured to execute the instructions to perform operations comprising:
determining, using an artificial intelligence (AI) system, a salient region overlay for at least one digitized image of the pathology specimen;
suppressing, based on a diagnostic value for each pixel, one or more non-salient regions of the at least one digitized image;
normalizing the salient region overlay to obtain a variable, the salient region overlay represented by a binary segmentation of the at least one digitized image indicating if each pixel has a salient feature present; and
representing the salient region overlay by a semantic segmentation of the at least one digitized image indicating a score or probability for each pixel.
20. The system of claim 19 , further comprising representing the salient region overlay by a set of super-pixels associated with a score or a probability for the salient feature being present or absent.